Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2861 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.7417. Min Act: -0.0000

Data Index: 549089 (The Pile)

Max Activating Token Index: 322

Text #1

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.6845. Min Act: -0.0000

Data Index: 82432 (The Pile)

Max Activating Token Index: 828

Text #2

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.7234. Min Act: -0.0000

Data Index: 1933628 (The Pile)

Max Activating Token Index: 254

Text #3

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.6262. Min Act: -0.0000

Data Index: 1783684 (The Pile)

Max Activating Token Index: 956

Text #4

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.6547. Min Act: 0.0000

Data Index: 1279304 (The Pile)

Max Activating Token Index: 426

Text #5

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.6587. Min Act: -0.0000

Data Index: 1801137 (The Pile)

Max Activating Token Index: 288

Text #6

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.6473. Min Act: -0.0000

Data Index: 1702128 (The Pile)

Max Activating Token Index: 39

Text #7

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.6047. Min Act: -0.0000

Data Index: 529185 (The Pile)

Max Activating Token Index: 883

Text #8

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.5948. Min Act: -0.0000

Data Index: 1083618 (The Pile)

Max Activating Token Index: 290

Text #9

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.6293. Min Act: -0.0000

Data Index: 619830 (The Pile)

Max Activating Token Index: 449

Text #10

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.5845. Min Act: -0.0000

Data Index: 1669061 (The Pile)

Max Activating Token Index: 237

Text #11

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.5782. Min Act: -0.0000

Data Index: 106827 (The Pile)

Max Activating Token Index: 178

Text #12

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.5562. Min Act: -0.0000

Data Index: 288277 (The Pile)

Max Activating Token Index: 127

Text #13

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.5749. Min Act: -0.0000

Data Index: 843895 (The Pile)

Max Activating Token Index: 21

Text #14

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.5899. Min Act: -0.0000

Data Index: 82979 (The Pile)

Max Activating Token Index: 128

Text #15

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.6194. Min Act: -0.0000

Data Index: 1545697 (The Pile)

Max Activating Token Index: 700

Text #16

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.5992. Min Act: -0.0000

Data Index: 1278855 (The Pile)

Max Activating Token Index: 477

Text #17

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.5627. Min Act: -0.0000

Data Index: 1532861 (The Pile)

Max Activating Token Index: 895

Text #18

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.5635. Min Act: -0.0000

Data Index: 917976 (The Pile)

Max Activating Token Index: 1022

Text #19

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.5578. Min Act: -0.0000

Data Index: 1323974 (The Pile)

Max Activating Token Index: 728